© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114854
    Prev
    Next
    INDEX
    Explanations

    potential outcomes or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chet
    -0.10
    idar
    -0.09
    allow
    -0.09
    使
    -0.09
     Busy
    -0.09
     Gould
    -0.09
     permet
    -0.09
    egin
    -0.08
    itr
    -0.08
     Hogan
    -0.08
    POSITIVE LOGITS
     becomes
    0.20
     benef
    0.18
     suffers
    0.18
     smoother
    0.18
     benefited
    0.17
     become
    0.17
     easier
    0.16
     improved
    0.16
     suffer
    0.15
     unaffected
    0.15
    Activations Density 0.446%

    No Known Activations